Abstract:
Picture Wise Perception-oriented image and video processing uses Just Noticeable Difference (PW-JND), the minimum difference a human visual system can perceive. Conventional Just Noticeable Difference (JND) models calculate the JND threshold for each pixel or sub-band separately, which may not accurately reflect a picture’s masking effect.
This project proposes a deep learning-based image compression PW-JND prediction model. First, we formulate PW-JND prediction as a multi-class classification problem and propose a framework to transform it into a binary classification problem solved by one binary classifier.
Second, we build a deep learning-based binary classifier called perceptually lossy/lossless predictor to predict whether an image is lossy to another. Finally, we propose a sliding window-based search strategy to predict PW-JND using the perceptually lossy/lossless predictor’s results.
Experimental results show that the proposed PW-JND model outperforms conventional JND models with a mean accuracy of 92% and an average absolute prediction error of 0.79 dB.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
